
Official updates for developers building on @CoreWeave. CoreWeave Forge, Weights & Biases Models, inference, sandboxes, and evals.
San Francisco
Joined May 2018
- Tweets9K
- Following1.3K
- Followers49.3K
- Likes12.1K
Las Vegas GP is this week 🏁
@thecodingsoup built his own AI race engineer to cut his lap time at @f1 Vegas.
Open-source models running locally, live telemetry streamed between two machines, and every radio call traced in @coreweave Agent Lens to catch the answers that go wrong.
Small models have a habit: they repeat whatever they just heard.
So @TheCodingSoup built a tiny town of @liquidai LFM2.5 agents, traced every line into @CoreWeave Agent Lens, and tagged the repeats.
No fine-tuning, just a harness, and the traces proved it worked: repeated lines dropped from 58% → 13%.
Best part: it's all plain OpenTelemetry from Swift. No Python or TypeScript SDK needed.
Optuna and Ax now run your search in Weights & Biases Sweeps.
Pick your engine with one line in sweep.yaml. Losing trials stop early, and you can weigh accuracy against latency in one sweep.
pip install "wandb[optuna]>=0.31.0" or send your agent here ⇢ crwv.co/uuIbs
Replying to @TheCodingSoup
@TheCodingSoup wanted to see how AI agents talk to each other when they work as a team.
So he gave a swarm a shared memory and let them do their thing inside of a @CoreWeave Sandbox. They wrote 12 notes. Not one got read by another agent. (Every agent was traced in Agent Lens, so we could check.)
The next run changed the timing: leads shared plans before starting, and each new agent got the relevant notes with its task. No duplicated experiments that time.
Try out Agent Lens bit.ly/4z4ELRf
Karpathy got annoyed with YouTube recs and built HackerTube in a weekend. Yours was probably manually lining up logged images to check a single detection.
New in Weights & Biases Models: zoom or pan one image and the rest follow at the same zoom level and position. Bounding boxes, masks, and class labels move with their images.
It's on by default, so the cropped screenshots can retire. crwv.co/uurrz
wandb 0.31.0 is out now, and import wandb and the CLI start about twice as fast.
That's for builders like @Vanzllll, whose DiffusionART team "found some surprising answers" after nearly 800 wandb runs.
Now find yours.
It also grows W&B LEET, the terminal UI for exploring W&B runs. wandb leet inspect --summary reads a run's local .wandb file, and --json prints that as JSON for a coding agent.
pip install -U wandb
iPhone Duo is out today, and Weights & Biases Models already supports 2-fold validation 📲
Folded, the cover screen tells you the run is still alive.
Unfold it, and your runs sit next to your panels on the big inner screen.
Hide a run, and every chart redraws right away, making the one that spiked much easier to find.
The app is free and ready for your Duo on day one. crwv.co/ut17n
AI teams are moving from prototypes to production faster than ever, but rapid development can create new blind spots.
Join us this Wednesday at 10:00 AM PT for the latest What's New Wednesdays session, and get valuable insights on vibe-coding, tracing, and deploying your agents.
Reserve your spot here: utm.io/ur8ga

